Too many people think because something finally “works”, it’s good. Once your AI has written code that seems to work, that’s supposed to be when the human starts their work.

Holy shit, preach!

Once you give a shit ton of prompts and the feature finally starts working, the code is most likely complete ass, probably filled with a ton of useless leftovers from previous iterations, redundant and unoptimized code. That’s when you start reading/understanding the code and polishing it, not when you ship it lol